
Builds valid PromQL queries for Google Cloud Monitoring metrics and resources
- Open source
- 24.4K GitHub stars
- Cloud and infrastructure

Builds valid PromQL queries for Google Cloud Monitoring metrics and resources

Guides setup and synthetic path monitoring for Google Cloud Network Insights with AppNeta

Lets your agent handle Google Cloud work through the Cloud Operator MCP server

Walks you through creating a Google Cloud operator agent via the autocloud MCP server

Copies your existing Google Cloud operating notes into the cloud operator agent's memory

Generates Terraform PromQL alert policies for Cloud Run services, jobs and worker pools

Lets your agent deploy and manage Cloud Run services, jobs and worker pools

Lets your agent search Cloud Trace spans and diagnose latency or errors on Google Cloud

Checks future GPU and TPU capacity windows and drafts calendar-mode reservation requests

Diagnoses unexpected Compute Engine VM reboots, stops and preemptions from host events

Diagnoses and fixes Compute Engine managed instance group autoscaling failures

Inspects and manages Google Compute Engine On-Demand reservations and their consumed

Checks whether Google Compute Engine Spot VM capacity is likely available before you

Guides planning and provisioning of standalone Compute Engine VMs via gcloud or MCP

Maps downstream tables, views and processes affected when a BigQuery asset changes

Lets an agent reserve, connect to, and manage remote Android devices on Google's DDP

Sets up the Firebase CLI, logs in, selects or creates projects, and fetches app config

Create, configure, list, update and delete stateful Gemini agents via REST

Diagnoses and mitigates GKE GPU and TPU node disruptions from host maintenance events

Diagnoses GKE JobSet restarts, preemptions and node failures for AI training jobs

Diagnoses GKE TPU and GPU nodes stuck NotReady after kernel panics or hardware lockups

Inspect, troubleshoot and validate GKE TPU dynamic slice resources and workloads

Monitors GKE TPU nodes, node pools and workloads using system metrics and PromQL

Guides agents through diagnosing GKE TPU multi-slice training hangs using MXLA analyzer

Diagnoses GKE TPU SliceCreationFailed errors caused by overlapping partitions or nodes

Diagnoses GKE TPU training throughput drops using ML Diagnostics and Cloud Monitoring

Diagnoses GKE TPU node pool stockouts caused by unhealthy pools holding reservation slots

Diagnoses GKE TPU slice creation stalls caused by unstable Compute Engine MIGs

Diagnoses vbar_control_agent OOMs and TPU v6e device failures on GKE clusters

Diagnoses GKE TPU VMs stuck in Compute Engine REPAIRING state and routes recovery